Hugging Face's logo

Xenova
/
gpt2

Text Generation
Transformers.js
ONNX
gpt2
Model card Files Community
Xenova HF staff commited on
Commit
2b6f8ca
•
1 Parent(s): 965dc1c

Upload folder using huggingface_hub

Browse files
Files changed (9) hide show
  1. config.json +1 -1
  2. generation_config.json +1 -1
  3. onnx/decoder_model.onnx +2 -2
  4. onnx/decoder_model_merged.onnx +2 -2
  5. onnx/decoder_model_merged_quantized.onnx +2 -2
  6. onnx/decoder_model_quantized.onnx +2 -2
  7. onnx/decoder_with_past_model.onnx +2 -2
  8. onnx/decoder_with_past_model_quantized.onnx +2 -2
  9. quantize_config.json +97 -0
config.json CHANGED
@@ -32,7 +32,7 @@
32
  "max_length": 50
33
  }
34
  },
35
- "transformers_version": "4.29.2",
36
  "use_cache": true,
37
  "vocab_size": 50257
38
  }
 
32
  "max_length": 50
33
  }
34
  },
35
+ "transformers_version": "4.33.0.dev0",
36
  "use_cache": true,
37
  "vocab_size": 50257
38
  }
generation_config.json CHANGED
@@ -2,5 +2,5 @@
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
- "transformers_version": "4.29.2"
6
  }
 
2
  "_from_model_config": true,
3
  "bos_token_id": 50256,
4
  "eos_token_id": 50256,
5
+ "transformers_version": "4.33.0.dev0"
6
  }
onnx/decoder_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd9d2cc37ed20cf78f52c9f424c61b1605fe88cbce371729198ded0549fed5d9
3
- size 653666800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b6c4c75bafa80ef5098219808b83d702f0a11524de52c21603ff30e2813213f7
3
+ size 499275976
onnx/decoder_model_merged.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:02058bf4773cf0665bd536d1290411ac587a144573590e5fff5e2b18201ef231
3
- size 654142857
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6aa1de057398705e99e1088f7ff2ef1a04edb19f7a4f2a0ae36fdd76c8d0349
3
+ size 500799139
onnx/decoder_model_merged_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b25d2fad539d895cad1969530dc77508b5524e06f581215349b503a8f52547d0
3
- size 166536066
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3633bbcb515767629ce17ff7ac1c3bd337f260a1135fb8c76fd9fe0dab876d19
3
+ size 128315766
onnx/decoder_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:8d5cd0010dac8c74efd687589b5dcee35e4480c313c7afb7e611cacbd6980792
3
- size 165823091
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419f6a0fe721ce9f41f35512347c58132b2e178310454231ca6ec04ff5029445
3
+ size 126556880
onnx/decoder_with_past_model.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:11ed625b30dcdc8777a608c4b3667626faec14d4e9fd7be2e586731fdc9e1700
3
- size 653673608
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9640de43faceabd4ebab467d3b5517dcad4e9eaa1d254e6762640a6965ece3f9
3
+ size 499282782
onnx/decoder_with_past_model_quantized.onnx CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:7721b8afee3c3ab47485e52e07422e2631f49955865d6fcff20f7c9bd69c82f6
3
- size 165832141
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f65bfa5c0d033ca3db23ece03d34c12d87ea2e7b3007b8944e4a9122ee64e029
3
+ size 126565928
quantize_config.json ADDED
@@ -0,0 +1,97 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "per_channel": false,
3
+ "reduce_range": false,
4
+ "per_model_config": {
5
+ "decoder_model": {
6
+ "op_types": [
7
+ "Pow",
8
+ "Sqrt",
9
+ "Softmax",
10
+ "Shape",
11
+ "Concat",
12
+ "Gather",
13
+ "ReduceMean",
14
+ "Div",
15
+ "MatMul",
16
+ "Slice",
17
+ "Transpose",
18
+ "Mul",
19
+ "Sub",
20
+ "Constant",
21
+ "ConstantOfShape",
22
+ "Tanh",
23
+ "Reshape",
24
+ "Where",
25
+ "Squeeze",
26
+ "Split",
27
+ "Range",
28
+ "Cast",
29
+ "Add",
30
+ "Gemm",
31
+ "Unsqueeze"
32
+ ],
33
+ "weight_type": "QInt8"
34
+ },
35
+ "decoder_model_merged": {
36
+ "op_types": [
37
+ "Pow",
38
+ "Sqrt",
39
+ "Softmax",
40
+ "Shape",
41
+ "Concat",
42
+ "Gather",
43
+ "ReduceMean",
44
+ "Div",
45
+ "MatMul",
46
+ "Slice",
47
+ "Transpose",
48
+ "Mul",
49
+ "Sub",
50
+ "Constant",
51
+ "ConstantOfShape",
52
+ "Tanh",
53
+ "Reshape",
54
+ "Where",
55
+ "Squeeze",
56
+ "If",
57
+ "Range",
58
+ "Split",
59
+ "Cast",
60
+ "Add",
61
+ "Gemm",
62
+ "Unsqueeze"
63
+ ],
64
+ "weight_type": "QInt8"
65
+ },
66
+ "decoder_with_past_model": {
67
+ "op_types": [
68
+ "Pow",
69
+ "Sqrt",
70
+ "Softmax",
71
+ "Shape",
72
+ "Concat",
73
+ "Gather",
74
+ "ReduceMean",
75
+ "Div",
76
+ "MatMul",
77
+ "Slice",
78
+ "Transpose",
79
+ "Mul",
80
+ "Sub",
81
+ "Constant",
82
+ "ConstantOfShape",
83
+ "Tanh",
84
+ "Reshape",
85
+ "Where",
86
+ "Squeeze",
87
+ "Split",
88
+ "Range",
89
+ "Cast",
90
+ "Add",
91
+ "Gemm",
92
+ "Unsqueeze"
93
+ ],
94
+ "weight_type": "QInt8"
95
+ }
96
+ }
97
+ }